Thanks to their different senses, human observers acquire multiple information coming from their environment. Complex cross-modal interactions occur during this perceptual process. This article proposes a framework to analyze and model these interactions through a rigorous and systematic data-driven process. This requires considering the general relationships between the physical events or factors involved in the process, not only in quantitative terms, but also in term of the influence of one factor on another. We use tools from information theory and probabilistic reasoning to derive relationships between the random variables of interest, where the central notion is that of conditional independence. Using mutual information analysis to guide the model elicitation process, a probabilistic causal model encoded as a Bayesian network is obtained. We exemplify the method by using data collected in an audio-visual localization task for human subjects, and we show that it yields a well-motivated model with good predictive ability. The model elicitation process offers new prospects for the investigation of the cognitive mechanisms of multisensory perception.

Abstract-A method that exploits an information theoretic framework to extract optimized audio features using video information is presented. A simple measure of mutual information (MI) between the resulting audio and video features allows the detection of the active speaker among different candidates. This method involves the optimization of an MI-based objective function. No approximation is needed to solve this optimization problem, neither for the estimation of the probability density functions (pdfs) of the features, nor for the cost function itself. The pdfs are estimated from the samples using a nonparametric approach. The challenging optimization problem is solved using a global method: the differential evolution algorithm. Two information theoretic optimization criteria are compared and their ability to extract audio features specific to speech production is discussed. Using these specific audio features, candidate video features are then classified as member of the "speaker" or "non-speaker" class, resulting in a speaker detection scheme. As a result, our method achieves a speaker detection rate of 100% on in-house test sequences, and of 85% on most commonly used sequences.

The sparse information captured by the sensory systems is used by the brain to apprehend the environment, for example, to spatially locate the source of audiovisual stimuli. This is an ill-posed inverse problem whose inherent uncertainty can be solved by jointly processing the information, as well as introducing constraints during this process, on the way this multisensory information is handled. This process and its result - the percept - depend on the contextual conditions perception takes place in. To date, perception has been investigated and modeled on the basis of either one of two of its dimensions: the percept or the temporal dynamics of the process. Here, we extend our previously proposed audiovisual perception model to predict both these dimensions to capture the phenomenon as a whole. Starting from a behavioral analysis, we use a data-driven approach to elicit a Bayesian network which infers the different percepts and dynamics of the process. Context-specific independence analyses enable us to use the model's structure to directly explore how different contexts affect the way subjects handle the same available information. Hence, we establish that, while the percepts yielded by a unisensory stimulus or by the non-fusion of multisensory stimuli may be similar, they result from different processes, as shown by their differing temporal dynamics. Moreover, our model predicts the impact of bottom-up (stimulus driven) factors as well as of top-down factors (induced by instruction manipulation) on both the perception process and the percept itself.

This paper presents an approach based on Bayesian Networks to estimate the workload of operators. The models take as inputs the entropy of different number of physiological features, as well as a cognitive feature (reaction time to a secondary task). They output the workload variation of subjects involved in successive tasks demanding different levels of cognitive resources. The performances of the classifiers are discussed in term of two criteria to be jointly optimized: the diversity, i.e. the ability of the model to perform on different subjects, and the accuracy, i.e., how close from the (subjectively estimated) workload level the model prediction is.